Change search
ReferencesLink to record
Permanent link

Direct link
A parallel QZ algorithm for distributed memory HPC systems
Umeå University, Faculty of Science and Technology, Department of Computing Science. Umeå University, Faculty of Science and Technology, High Performance Computing Center North (HPC2N).
Umeå University, Faculty of Science and Technology, Department of Computing Science. Umeå University, Faculty of Science and Technology, High Performance Computing Center North (HPC2N).
2014 (English)In: SIAM Journal on Scientific Computing, ISSN 1064-8275, E-ISSN 1095-7197, Vol. 36, no 5, C480-C503 p.Article in journal (Refereed) Published
Abstract [en]

Appearing frequently in applications, generalized eigenvalue problems represent one of the core problems in numerical linear algebra. The QZ algorithm of Moler and Stewart is the most widely used algorithm for addressing such problems. Despite its importance, little attention has been paid to the parallelization of the QZ algorithm. The purpose of this work is to fill this gap. We propose a parallelization of the QZ algorithm that incorporates all modern ingredients of dense eigensolvers, such as multishift and aggressive early deflation techniques. To deal with (possibly many) infinite eigenvalues, a new parallel deflation strategy is developed. Numerical experiments for several random and application examples demonstrate the effectiveness of our algorithm on two different distributed memory HPC systems.

Place, publisher, year, edition, pages
SIAM publications , 2014. Vol. 36, no 5, C480-C503 p.
Keyword [en]
generalized eigenvalue problem, nonsymmetric QZ algorithm, multishift, bulge chasing, infinite genvalues, parallel algorithms, level 3 performance, aggressive early deflation, MMEL J, 1993, ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, V19, P175
National Category
Mathematics Computer Science
URN: urn:nbn:se:umu:diva-97903DOI: 10.1137/140954817ISI: 000346123200025OAI: diva2:779112
Available from: 2015-01-12 Created: 2015-01-08 Last updated: 2016-05-04Bibliographically approved
In thesis
1. Parallel Algorithms and Library Software for the Generalized Eigenvalue Problem on Distributed Memory Computer Systems
Open this publication in new window or tab >>Parallel Algorithms and Library Software for the Generalized Eigenvalue Problem on Distributed Memory Computer Systems
2016 (English)Licentiate thesis, comprehensive summary (Other academic)
Alternative title[sv]
Parallella algoritmer och biblioteksprogramvara för det generaliserade egenvärdesproblemet på datorsystem med distribuerat minne
Abstract [en]

We present and discuss algorithms and library software for solving the generalized non-symmetric eigenvalue problem (GNEP) on high performance computing (HPC) platforms with distributed memory. Such problems occur frequently in computational science and engineering, and our contributions make it possible to solve GNEPs fast and accurate in parallel using state-of-the-art HPC systems. A generalized eigenvalue problem corresponds to finding scalars y and vectors x such that Ax = yBx, where A and B are real square matrices. A nonzero x that satisfies the GNEP equation is called an eigenvector of the ordered pair (A,B), and the scalar y is the associated eigenvalue. Our contributions include parallel algorithms for transforming a matrix pair (A,B) to a generalized Schur form (S,T), where S is quasi upper triangular and T is upper triangular. The eigenvalues are revealed from the diagonals of S and T. Moreover, for a specified set of eigenvalues an associated pair of deflating subspaces can be computed, which typically is requested in various applications. In the first stage the matrix pair (A,B) is reduced to a Hessenberg-triangular form (H,T), where H is upper triangular with one nonzero subdiagonal and T is upper triangular, in a finite number of steps. The second stage reduces the matrix pair further to generalized Schur form (S,T) using an iterative QZ-based method. Outgoing from a one-stage method for the reduction from (A,B) to (H,T), a novel parallel algorithm is developed. In brief, a delayed update technique is applied to several partial steps, involving low level operations, before associated accumulated transformations are applied in a blocked fashion which together with a wave-front task scheduler makes the algorithm scale when running in a parallel setting. The potential presence of infinite eigenvalues makes a generalized eigenvalue problem ill-conditioned. Therefore the parallel algorithm for the second stage, reduction to (S,T) form, continuously scan for and robustly deflate infinite eigenvalues. This will reduce the impact so that they do not interfere with other real eigenvalues or are misinterpreted as real eigenvalues. In addition, our parallel iterative QZ-based algorithm makes use of multiple implicit shifts and an aggressive early deflation (AED) technique, which radically speeds up the convergence. The multi-shift strategy is based on independent chains of so called coupled bulges and computational windows which is an important source of making the algorithm scalable. The parallel algorithms have been implemented in state-of-the-art library software. The performance is demonstrated and evaluated using up to 1600 CPU cores for problems with matrices as large as 100000 x 100000. Our library software is described in a User Guide. The software is, optionally, tunable via a set of parameters for various thresholds and buffer sizes etc. These parameters are discussed, and recommended values are specified which should result in reasonable performance on HPC systems similar to the ones we have been running on.

Place, publisher, year, edition, pages
Umeå: Umeå universitet, 2016. 18 p.
Report / UMINF, ISSN 0348-0542 ; 16.11
National Category
Computer Science
Research subject
Computer and Information Science
urn:nbn:se:umu:diva-119439 (URN)978-91-7601-491-2 (ISBN)
2016-05-27, MC313, Umeå universitet, Umeå, 10:00 (English)
Available from: 2016-04-19 Created: 2016-04-19 Last updated: 2016-05-04Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Adlerborn, BjörnKågström, Bo
By organisation
Department of Computing ScienceHigh Performance Computing Center North (HPC2N)
In the same journal
SIAM Journal on Scientific Computing
MathematicsComputer Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 99 hits
ReferencesLink to record
Permanent link

Direct link